Actor-critic (AC) methods are widely used in reinforcement learning (RL)...
We consider minimizing functions for which it is expensive to compute th...
We consider online imitation learning (OIL), where the task is to find a...
In contrast to the advances in characterizing the sample complexity for
...
We study policy optimization in an infinite horizon, γ-discounted
constr...
We design step-size schemes that make stochastic gradient descent (SGD)
...
We use functional mirror ascent to propose a general framework (referred...
Variance reduction (VR) methods for finite-sum minimization typically re...
As adaptive gradient methods are typically used for training
over-parame...
We propose a stochastic variant of the classical Polyak step-size (Polya...
We propose RandUCB, a bandit strategy that uses theoretically derived
co...
We consider stochastic second order methods for minimizing strongly-conv...
Recent works have shown that stochastic gradient descent (SGD) achieves ...
Modern machine learning focuses on highly expressive models that are abl...
Bayesian optimization and Lipschitz optimization have developed alternat...
We investigate the use of bootstrapping in the bandit setting. We first ...
We study the stochastic online problem of learning to influence in a soc...
We consider the problem of influence maximization, the problem of
maximi...
Automated detection of visually salient regions is an active area of res...